MétaCan
Menu
Back to cohort
Record W7096680464

Reinforcement Learning for Factored Markov Decision Processes

2002· article· en· W7096680464 on OpenAlexfundno aff

Bibliographic record

VenueTSpace · 2002
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsReinforcement learningMarkov decision processInferencePartially observable Markov decision processRepresentation (politics)Core (optical fiber)Action (physics)State (computer science)Markov processQ-learning
DOInot available

Abstract

fetched live from OpenAlex

Learning to act optimally in a complex, dynamic and noisy environment is a hard prob-lem. Various threads of research from reinforcement learning, animal conditioning, oper-ations research, machine learning, statistics and optimal control are beginning to come together to offer solutions to this problem. I present a thesis in which novel algorithms are presented for learning the dynamics, learning the value function, and selecting good actions for Markov decision processes. The problems considered have high-dimensional factored state and action spaces, and are either fully or partially observable. The ap-proach I take is to recognize similarities between the problems being solved in the rein-forcement learning and graphical models literature, and to use and combine techniques from the two fields in novel ways. In particular I present two new algorithms. First, the DBN algorithm learns a compact representation of the core process of a partially observable MDP. Because inference in the DBN is intractable, I use approximate inference to maintain the belief state. A belief-state action-value function is learned using reinforcement learning. I show that this DBN algorithm can solve POMDPs with very large state spaces and useful hidden state.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.880
Threshold uncertainty score0.642

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.038
GPT teacher head0.305
Teacher spread0.267 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2002
Admission routes1
Has abstractyes

Explore more

Same venueTSpaceSame topicReinforcement Learning in RoboticsFrench-language works237,207